About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Sosuke Nishikawa
- sl:arxiv_num : 2205.04260
- sl:arxiv_published : 2022-05-09T13:22:44Z
- sl:arxiv_summary : We present EASE, a novel method for learning sentence embeddings via
contrastive learning between sentences and their related entities. The
advantage of using entity supervision is twofold: (1) entities have been shown
to be a strong indicator of text semantics and thus should provide rich
training signals for sentence embeddings; (2) entities are defined
independently of languages and thus offer useful cross-lingual alignment
supervision. We evaluate EASE against other unsupervised models both in
monolingual and multilingual settings. We show that EASE exhibits competitive
or better performance in English semantic textual similarity (STS) and short
text clustering (STC) tasks and it significantly outperforms baseline methods
in multilingual settings on a variety of tasks. Our source code, pre-trained
models, and newly constructed multilingual STC dataset are available at
https://github.com/studio-ousia/ease.@en
- sl:arxiv_title : EASE: Entity-Aware Contrastive Learning of Sentence Embedding@en
- sl:arxiv_updated : 2022-05-09T13:22:44Z
- sl:bookmarkOf : https://arxiv.org/abs/2205.04260
- sl:creationDate : 2022-05-11
- sl:creationTime : 2022-05-11T01:25:12Z
Documents with similar tags (experimental)